The standard way of training video models entails sampling at each iteration a single clip from a video and optimizing the clip prediction with respect to the video-level label. We argue that a single clip may not have enough temporal coverage to exhibit the label to recognize, since video datasets are often weakly labeled with categorical information but without dense temporal annotations. Furthermore, optimizing the model over brief clips impedes its ability to learn long-term temporal dependencies. To overcome these limitations, we introduce a collaborative memory mechanism that encodes information across multiple sampled clips of a video at each training iteration. This enables the learning of long-range dependencies beyond a single clip. We explore different design choices for the collaborative memory to ease the optimization difficulties. Our proposed framework is end-to-end trainable and significantly improves the accuracy of video classification at a negligible computational overhead. Through extensive experiments, we demonstrate that our framework generalizes to different video architectures and tasks, outperforming the state of the art on both action recognition (e.g., Kinetics-400 & 700, Charades, Something-Something-V1) and action detection (e.g., AVA v2.1 & v2.2).
We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches. Our experimental study compares different self-attention schemes and suggests that "divided attention," where temporal attention and spatial attention are separately applied within each block, leads to the best video classification accuracy among the design choices considered. Despite the radically different design compared to the prominent paradigm of 3D convolutional architectures for video, TimeSformer achieves state-of-the-art results on several major action recognition benchmarks, including the best reported accuracy on Kinetics-400 and Kinetics-600. Furthermore, our model is faster to train and has higher test-time efficiency compared to competing architectures. Code and pretrained models will be made publicly available.
Although speaker verification has conventionally been an audio-only task, some practical applications provide both audio and visual streams of input. In these cases, the visual stream provides complementary information and can often be leveraged in conjunction with the acoustics of speech to improve verification performance. In this study, we explore audio-visual approaches to speaker verification, starting with standard fusion techniques to learn joint audio-visual (AV) embeddings, and then propose a novel approach to handle cross-modal verification at test time. Specifically, we investigate unimodal and concatenation based AV fusion and report the lowest AV equal error rate (EER) of 0.7% on the VoxCeleb1 dataset using our best system. As these methods lack the ability to do cross-modal verification, we introduce a multi-view model which uses a shared classifier to map audio and video into the same space. This new approach achieves 28% EER on VoxCeleb1 in the challenging testing condition of cross-modal verification.
We present \textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each modality is first converted into a set of language embeddings by a learnable tokenizer. This allows our approach to perform multimodal fusion in the language space, thus eliminating the need for ad-hoc cross-modal fusion modules. To address the non-differentiability of tokenization on continuous inputs (e.g., video or audio), we utilize a relaxation scheme that enables end-to-end training. Furthermore, unlike prior encoder-only models, our network includes an autoregressive decoder to generate open-ended text from the multimodal embeddings fused by the language encoder. This renders our approach fully generative and makes it directly applicable to different "video+$x$ to text" problems without the need to design specialized network heads for each task. The proposed framework is not only conceptually simple but also remarkably effective: experiments demonstrate that our approach based on a single architecture outperforms the state-of-the-art on three video-based text-generation tasks -- captioning, question answering and audio-visual scene-aware dialog.
With the rise of deep learning, there has been increased interest in using neural networks for histopathology image analysis, a field that investigates the properties of biopsy or resected specimens that are traditionally manually examined under a microscope by pathologists. In histopathology image analysis, however, challenges such as limited data, costly annotation, and processing high-resolution and variable-size images create a high barrier of entry and make it difficult to quickly iterate over model designs. Throughout scientific history, many significant research directions have leveraged small-scale experimental setups as petri dishes to efficiently evaluate exploratory ideas, which are then validated in large-scale applications. For instance, the Drosophila fruit fly in genetics and MNIST in computer vision are well-known petri dishes. In this paper, we introduce a minimalist histopathology image analysis dataset (MHIST), an analogous petri dish for histopathology image analysis. MHIST is a binary classification dataset of 3,152 fixed-size images of colorectal polyps, each with a gold-standard label determined by the majority vote of seven board-certified gastrointestinal pathologists and annotator agreement level. MHIST occupies less than 400 MB of disk space, and a ResNet-18 baseline can be trained to convergence on MHIST in just 6 minutes using 3.5 GB of memory on a NVIDIA RTX 3090. As example use cases, we use MHIST to study natural questions such as how dataset size, network depth, transfer learning, and high-disagreement examples affect model performance. By introducing MHIST, we hope to not only help facilitate the work of current histopathology imaging researchers, but also make histopathology image analysis more accessible to the general computer vision community. Our dataset is available at https://bmirds.github.io/MHIST.
We present \textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each modality is first converted into a set of language embeddings by a learnable tokenizer. This allows our approach to perform multimodal fusion in the language space, thus eliminating the need for ad-hoc cross-modal fusion modules. To address the non-differentiability of tokenization on continuous inputs (e.g., video or audio), we utilize a relaxation scheme that enables end-to-end training. Furthermore, unlike prior encoder-only models, our network includes an autoregressive decoder to generate open-ended text from the multimodal embeddings fused by the language encoder. This renders our approach fully generative and makes it directly applicable to different "video+$x$ to text" problems without the need to design specialized network heads for each task. The proposed framework is not only conceptually simple but also remarkably effective: experiments demonstrate that our approach based on a single architecture outperforms the state-of-the-art on three video-based text-generation tasks -- captioning, question answering and audio-visual scene-aware dialog.
In contrast to traditional weight optimization in a continuous space, we demonstrate the existence of effective random networks whose weights are never updated. By selecting a weight among a fixed set of random values for each individual connection, our method uncovers combinations of random weights that match the performance of traditionally-trained networks of the same capacity. We refer to our networks as "slot machines" where each reel (connection) contains a fixed set of symbols (random values). Our backpropagation algorithm "spins" the reels to seek "winning" combinations, i.e., selections of random weight values that minimize the given loss. Quite surprisingly, we find that allocating just a few random values to each connection (e.g., 8 values per connection) yields highly competitive combinations despite being dramatically more constrained compared to traditionally learned weights. Moreover, finetuning these combinations often improves performance over the trained baselines. A randomly initialized VGG-19 with 8 values per connection contains a combination that achieves 90% test accuracy on CIFAR-10. Our method also achieves an impressive performance of 98.1% on MNIST for neural networks containing only random weights.
Developing deep learning models to analyze histology images has been computationally challenging, as the massive size of the images causes excessive strain on all parts of the computing pipeline. This paper proposes a novel deep learning-based methodology for improving the computational efficiency of histology image classification. The proposed approach is robust when used with images that have reduced input resolution and can be trained effectively with limited labeled data. Pre-trained on the original high-resolution (HR) images, our method uses knowledge distillation (KD) to transfer learned knowledge from a teacher model to a student model trained on the same images at a much lower resolution. To address the lack of large-scale labeled histology image datasets, we perform KD in a self-supervised manner. We evaluate our approach on two histology image datasets associated with celiac disease (CD) and lung adenocarcinoma (LUAD). Our results show that a combination of KD and self-supervision allows the student model to approach, and in some cases, surpass the classification accuracy of the teacher, while being much more efficient. Additionally, we observe an increase in student classification performance as the size of the unlabeled dataset increases, indicating that there is potential to scale further. For the CD data, our model outperforms the HR teacher model, while needing 4 times fewer computations. For the LUAD data, our student model results at 1.25x magnification are within 3% of the teacher model at 10x magnification, with a 64 times computational cost reduction. Moreover, our CD outcomes benefit from performance scaling with the use of more unlabeled data. For 0.625x magnification, using unlabeled data improves accuracy by 4% over the baseline. Thus, our method can improve the feasibility of deep learning solutions for digital pathology with standard computational hardware.
Applying curriculum learning requires both a range of difficulty in data and a method for determining the difficulty of examples. In many tasks, however, satisfying these requirements can be a formidable challenge. In this paper, we contend that histopathology image classification is a compelling use case for curriculum learning. Based on the nature of histopathology images, a range of difficulty inherently exists among examples, and, since medical datasets are often labeled by multiple annotators, annotator agreement can be used as a natural proxy for the difficulty of a given example. Hence, we propose a simple curriculum learning method that trains on progressively-harder images as determined by annotator agreement. We evaluate our hypothesis on the challenging and clinically-important task of colorectal polyp classification. Whereas vanilla training achieves an AUC of 83.7% for this task, a model trained with our proposed curriculum learning approach achieves an AUC of 88.2%, an improvement of 4.5%. Our work aims to inspire researchers to think more creatively and rigorously when choosing contexts for applying curriculum learning.