Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in training data (e.g., if a word is present in 60% of training sentences, it might be predicted in 70% of sentences at test time). This can lead to incorrect captions in domains where unbiased captions are desired, or required, due to over-reliance on the learned prior and image context. In this work we investigate generation of gender-specific caption words (e.g. man, woman) based on the person's appearance or the image context. We introduce a new Equalizer model that ensures equal gender probability when gender evidence is occluded in a scene and confident predictions when gender evidence is present. The resulting model is forced to look at a person rather than use contextual cues to make a gender-specific predictions. The losses that comprise our model, the Appearance Confusion Loss and the Confident Loss, are general, and can be added to any description model in order to mitigate impacts of unwanted bias in a description dataset. Our proposed model has lower error than prior work when describing images with people and mentioning their gender and more closely matches the ground truth ratio of sentences including women to sentences including men. We also show that unlike other approaches, our model is indeed more often looking at people when predicting their gender.
Recently, the state-of-the-art models for image captioning have overtaken human performance based on the most popular metrics, such as BLEU, METEOR, ROUGE, and CIDEr. Does this mean we have solved the task of image captioning? The above metrics only measure the similarity of the generated caption to the human annotations, which reflects its accuracy. However, an image contains many concepts and multiple levels of detail, and thus there is a variety of captions that express different concepts and details that might be interesting for different humans. Therefore only evaluating accuracy is not sufficient for measuring the performance of captioning models --- the diversity of the generated captions should also be considered. In this paper, we proposed a new metric for measuring the diversity of image captions, which is derived from latent semantic analysis and kernelized to use CIDEr similarity. We conduct extensive experiments to re-evaluate recent captioning models in the context of both diversity and accuracy. We find that there is still a large gap between the model and human performance in terms of both accuracy and diversity and the models that have optimized accuracy (CIDEr) have low diversity. We also show that balancing the cross-entropy loss and CIDEr reward in reinforcement learning during training can effectively control the tradeoff between diversity and accuracy of the generated captions.
Despite continuously improving performance, contemporary image captioning models are prone to "hallucinating" objects that are not actually in a scene. One problem is that standard metrics only measure similarity to ground truth captions and may not fully capture image relevance. In this work, we propose a new image relevance metric to evaluate current models with veridical visual labels and assess their rate of object hallucination. We analyze how captioning model architectures and learning objectives contribute to object hallucination, explore when hallucination is likely due to image misclassification or language priors, and assess how well current sentence metrics capture object hallucination. We investigate these questions on the standard image captioning benchmark, MSCOCO, using a diverse set of models. Our analysis yields several interesting findings, including that models which score best on standard sentence metrics do not always have lower hallucination and that models which hallucinate more tend to make errors driven by language priors.
Recently, the state-of-the-art models for image captioning have overtaken human performance based on the most popular metrics, such as BLEU, METEOR, ROUGE, and CIDEr. Does this mean we have solved the task of image captioning? The above metrics only measure the similarity of the generated caption to the human annotations, which reflects its accuracy. However, an image contains many concepts and multiple levels of detail, and thus there is a variety of captions that express different concepts and details that might be interesting for different humans. Therefore only evaluating accuracy is not sufficient for measuring the performance of captioning models --- the diversity of the generated captions should also be considered. In this paper, we proposed a new metric for measuring the diversity of image captions, which is derived from latent semantic analysis and kernelized to use CIDEr similarity. We conduct extensive experiments to re-evaluate recent captioning models in the context of both diversity and accuracy. We find that there is still a large gap between the model and human performance in terms of both accuracy and diversity and the models that have optimized accuracy (CIDEr) have low diversity. We also show that balancing the cross-entropy loss and CIDEr reward in reinforcement learning during training can effectively control the tradeoff between diversity and accuracy of the generated captions.
Surrogate models for hotspot ignition and growth rates were presented in Part I, where the hotspots were formed by the collapse of single cylindrical voids. Such isolated cylindrical voids are idealizations of the void morphology in real meso-structures. This paper therefore investigates the effect of non-cylindrical void shapes and void-void interactions on hotspot ignition and growth. Surrogate models capturing these effects are constructed using a Bayesian Kriging approach. The training data for machine learning the surrogates are derived from reactive void collapse simulations spanning the parameter space of void aspect ratio (AR), void orientation ($\theta$), and void fraction ($\phi$). The resulting surrogate models portray strong dependence of the ignition and growth rates on void aspect ratio and orientation, particularly when they are oriented at acute angles with respect to the imposed shock. The surrogate models for void interaction effects show significant changes in hotspot ignition and growth rates as the void fraction increases. The paper elucidates the physics of hotspot evolution in void fields due to the creation and interaction of multiple hotspots. The results from this work will be useful not only for constructing meso-informed macro-scale models of HMX, but also for understanding the physics of void-void interactions and sensitivity due to void shape and orientation.
Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder-decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to be deployed on embedded system with limited hardware resources. This is because the size of word and output embedding matrices grow proportionally with the size of vocabulary, adversely affecting the compactness of these networks. To address this limitation, this paper introduces a brand new idea in the domain of image captioning. That is, we tackle the problem of compactness of image captioning models which is hitherto unexplored. We showed that, our proposed model, named COMIC for COMpact Image Captioning, achieves comparable results in five common evaluation metrics with state-of-the-art approaches on both MS-COCO and InstaPIC-1.1M datasets despite having an embedding vocabulary size that is 39x - 99x smaller
Stories are essential for genealogy research since they can help build emotional connections with people. A lot of family stories are reserved in historical photos and albums. Recent development on image captioning models makes it feasible to "tell stories" for photos automatically. The attention mechanism has been widely adopted in many state-of-the-art encoder-decoder based image captioning models, since it can bridge the gap between the visual part and the language part. Most existing captioning models implicitly trained attention modules with word-likelihood loss. Meanwhile, lots of studies have investigated intrinsic attentions for visual models using gradient-based approaches. Ideally, attention maps predicted by captioning models should be consistent with intrinsic attentions from visual models for any given visual concept. However, no work has been done to align implicitly learned attention maps with intrinsic visual attentions. In this paper, we proposed a novel model that measured consistency between captioning predicted attentions and intrinsic visual attentions. This alignment loss allows explicit attention correction without using any expensive bounding box annotations. We developed and evaluated our model on COCO dataset as well as a genealogical dataset from Ancestry.com Operations Inc., which contains billions of historical photos. The proposed model achieved better performances on all commonly used language evaluation metrics for both datasets.
In this work, we present a novel multi-modal dataset consisting of eye movements and verbal descriptions recorded synchronously over images. Using this data, we study the differences between human attention in free-viewing and image captioning tasks. We look into the relationship between human attention and language constructs during perception and sentence articulation. We also compare human and machine attention, in particular the top-down soft attention approach that is argued to mimick human attention, in captioning tasks. Our study reveals that, (1) human attention behaviour in free-viewing is different than image description as humans tend to fixate on a greater variety of regions under the latter task; (2) there is a strong relationship between the described objects and the objects attended by subjects ($97\%$ of described objects are being attended); (3) a convolutional neural network as feature encoder captures regions that human attend under image captioning to a great extent (around $78\%$); (4) the soft-attention as the top-down mechanism does not agree with human attention behaviour neither spatially nor temporally; and (5) soft-attention does not add strong beneficial human-like attention behaviour for the task of captioning as it has low correlation between caption scores and attention consistency scores, indicating a large gap between human and machine in regard to top-down attention.
Automatically generating the descriptions of an image, i.e., image captioning, is an important and fundamental topic in artificial intelligence, which bridges the gap between computer vision and natural language processing. Based on the successful deep learning models, especially the CNN model and Long Short-Term Memories (LSTMs) with attention mechanism, we propose a hierarchical attention model by utilizing both of the global CNN features and the local object features for more effective feature representation and reasoning in image captioning. The generative adversarial network (GAN), together with a reinforcement learning (RL) algorithm, is applied to solve the exposure bias problem in RNN-based supervised training for language problems. In addition, through the automatic measurement of the consistency between the generated caption and the image content by the discriminator in the GAN framework and RL optimization, we make the finally generated sentences more accurate and natural. Comprehensive experiments show the improved performance of the hierarchical attention mechanism and the effectiveness of our RL-based optimization method. Our model achieves state-of-the-art results on several important metrics in the MSCOCO dataset, using only greedy inference.
