The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks. Its simplicity and effectiveness have led to wide applications in the explanation of visual predictions and weakly-supervised localization tasks. However, CAM has its own shortcomings. The computation of attribution maps relies on ad-hoc calibration steps that are not part of the training computational graph, making it difficult for us to understand the real meaning of the attribution values. In this paper, we improve CAM by explicitly incorporating a latent variable encoding the location of the cue for recognition in the formulation, thereby subsuming the attribution map into the training computational graph. The resulting model, class activation latent mapping, or CALM, is trained with the expectation-maximization algorithm. Our experiments show that CALM identifies discriminative attributes for image classifiers more accurately than CAM and other visual attribution baselines. CALM also shows performance improvements over prior arts on the weakly-supervised object localization benchmarks. Our code is available at //github.com/naver-ai/calm.
相關內容
Predicting the future trajectory of a moving agent can be easy when the past trajectory continues smoothly but is challenging when complex interactions with other agents are involved. Recent deep learning approaches for trajectory prediction show promising performance and partially attribute this to successful reasoning about agent-agent interactions. However, it remains unclear which features such black-box models actually learn to use for making predictions. This paper proposes a procedure that quantifies the contributions of different cues to model performance based on a variant of Shapley values. Applying this procedure to state-of-the-art trajectory prediction methods on standard benchmark datasets shows that they are, in fact, unable to reason about interactions. Instead, the past trajectory of the target is the only feature used for predicting its future. For a task with richer social interaction patterns, on the other hand, the tested models do pick up such interactions to a certain extent, as quantified by our feature attribution method. We discuss the limits of the proposed method and its links to causality
As deep networks begin to be deployed as autonomous agents, the issue of how they can communicate with each other becomes important. Here, we train two deep nets from scratch to perform realistic referent identification through unsupervised emergent communication. We show that the largely interpretable emergent protocol allows the nets to successfully communicate even about object types they did not see at training time. The visual representations induced as a by-product of our training regime, moreover, show comparable quality, when re-used as generic visual features, to a recent self-supervised learning model. Our results provide concrete evidence of the viability of (interpretable) emergent deep net communication in a more realistic scenario than previously considered, as well as establishing an intriguing link between this field and self-supervised visual learning.
Self-supervised video representation methods typically focus on the representation of temporal attributes in videos. However, the role of stationary versus non-stationary attributes is less explored: Stationary features, which remain similar throughout the video, enable the prediction of video-level action classes. Non-stationary features, which represent temporally varying attributes, are more beneficial for downstream tasks involving more fine-grained temporal understanding, such as action segmentation. We argue that a single representation to capture both types of features is sub-optimal, and propose to decompose the representation space into stationary and non-stationary features via contrastive learning from long and short views, i.e. long video sequences and their shorter sub-sequences. Stationary features are shared between the short and long views, while non-stationary features aggregate the short views to match the corresponding long view. To empirically verify our approach, we demonstrate that our stationary features work particularly well on an action recognition downstream task, while our non-stationary features perform better on action segmentation. Furthermore, we analyse the learned representations and find that stationary features capture more temporally stable, static attributes, while non-stationary features encompass more temporally varying ones.
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions. Some recent papers have shown the importance of localized features together with fine-tuning the feature extractor to obtain discriminative and transferable features. However, these methods require complex attention or part detection modules to perform explicit localization in the visual space. In contrast, in this paper we propose localizing representations in the semantic/attribute space, with a simple but effective pipeline where localization is implicit. Focusing on attribute representations, we show that our method obtains state-of-the-art performance on CUB and SUN datasets, and also achieves competitive results on AWA2 dataset, outperforming generally more complex methods with explicit localization in the visual space. Our method can be implemented easily, which can be used as a new baseline for zero shot learning.
Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribution (OOD) generalization for various NLP tasks by constructing a new robustness benchmark with realistic distribution shifts. We measure the generalization of previous models including bag-of-words models, ConvNets, and LSTMs, and we show that pretrained Transformers' performance declines are substantially smaller. Pretrained transformers are also more effective at detecting anomalous or OOD examples, while many previous models are frequently worse than chance. We examine which factors affect robustness, finding that larger models are not necessarily more robust, distillation can be harmful, and more diverse pretraining data can enhance robustness. Finally, we show where future work can improve OOD robustness.
Most existing video summarisation methods are based on either supervised or unsupervised learning. In this paper, we propose a reinforcement learning-based weakly supervised method that exploits easy-to-obtain, video-level category labels and encourages summaries to contain category-related information and maintain category recognisability. Specifically, We formulate video summarisation as a sequential decision-making process and train a summarisation network with deep Q-learning (DQSN). A companion classification network is also trained to provide rewards for training the DQSN. With the classification network, we develop a global recognisability reward based on the classification result. Critically, a novel dense ranking-based reward is also proposed in order to cope with the temporally delayed and sparse reward problems for long sequence reinforcement learning. Extensive experiments on two benchmark datasets show that the proposed approach achieves state-of-the-art performance.
This paper addresses the problem of viewpoint estimation of an object in a given image. It presents five key insights that should be taken into consideration when designing a CNN that solves the problem. Based on these insights, the paper proposes a network in which (i) The architecture jointly solves detection, classification, and viewpoint estimation. (ii) New types of data are added and trained on. (iii) A novel loss function, which takes into account both the geometry of the problem and the new types of data, is propose. Our network improves the state-of-the-art results for this problem by 9.8%.
The task of face attribute manipulation has found increasing applications, but still remains challeng- ing with the requirement of editing the attributes of a face image while preserving its unique details. In this paper, we choose to combine the Variational AutoEncoder (VAE) and Generative Adversarial Network (GAN) for photorealistic image genera- tion. We propose an effective method to modify a modest amount of pixels in the feature maps of an encoder, changing the attribute strength contin- uously without hindering global information. Our training objectives of VAE and GAN are reinforced by the supervision of face recognition loss and cy- cle consistency loss for faithful preservation of face details. Moreover, we generate facial masks to en- force background consistency, which allows our training to focus on manipulating the foreground face rather than background. Experimental results demonstrate our method, called Mask-Adversarial AutoEncoder (M-AAE), can generate high-quality images with changing attributes and outperforms prior methods in detail preservation.
During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learning features for specific tasks has accelerated. For instance, discriminative visual tracking methods based on deep architectures have been studied with promising performance. Nevertheless, correlation filter based (CFB) trackers confine themselves to use the pre-trained networks which are trained for object classification problem. To this end, in this manuscript the problem of learning deep fully convolutional features for the CFB visual tracking is formulated. In order to learn the proposed model, a novel and efficient backpropagation algorithm is presented based on the loss function of the network. The proposed learning framework enables the network model to be flexible for a custom design. Moreover, it alleviates the dependency on the network trained for classification. Extensive performance analysis shows the efficacy of the proposed custom design in the CFB tracking framework. By fine-tuning the convolutional parts of a state-of-the-art network and integrating this model to a CFB tracker, which is the top performing one of VOT2016, 18% increase is achieved in terms of expected average overlap, and tracking failures are decreased by 25%, while maintaining the superiority over the state-of-the-art methods in OTB-2013 and OTB-2015 tracking datasets.
Discrete correlation filter (DCF) based trackers have shown considerable success in visual object tracking. These trackers often make use of low to mid level features such as histogram of gradients (HoG) and mid-layer activations from convolution neural networks (CNNs). We argue that including semantically higher level information to the tracked features may provide further robustness to challenging cases such as viewpoint changes. Deep salient object detection is one example of such high level features, as it make use of semantic information to highlight the important regions in the given scene. In this work, we propose an improvement over DCF based trackers by combining saliency based and other features based filter responses. This combination is performed with an adaptive weight on the saliency based filter responses, which is automatically selected according to the temporal consistency of visual saliency. We show that our method consistently improves a baseline DCF based tracker especially in challenging cases and performs superior to the state-of-the-art. Our improved tracker operates at 9.3 fps, introducing a small computational burden over the baseline which operates at 11 fps.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191