Matthew A. Brown

Daniel Davila, Dawei Du, Bryon Lewis et al.

In this paper, we present the Multi-view Extended Videos with Identities (MEVID) dataset for large-scale, video person re-identification (ReID) in the wild. To our knowledge, MEVID represents the most-varied video person ReID dataset, spanning an extensive indoor and outdoor environment across nine unique dates in a 73-day window, various camera viewpoints, and entity clothing changes. Specifically, we label the identities of 158 unique people wearing 598 outfits taken from 8, 092 tracklets, average length of about 590 frames, seen in 33 camera views from the very large-scale MEVA person activities dataset. While other datasets have more unique identities, MEVID emphasizes a richer set of information about each individual, such as: 4 outfits/identity vs. 2 outfits/identity in CCVID, 33 viewpoints across 17 locations vs. 6 in 5 simulated locations for MTA, and 10 million frames vs. 3 million for LS-VID. Being based on the MEVA video dataset, we also inherit data that is intentionally demographically balanced to the continental United States. To accelerate the annotation process, we developed a semi-automatic annotation framework and GUI that combines state-of-the-art real-time models for object detection, pose estimation, person ReID, and multi-object tracking. We evaluate several state-of-the-art methods on MEVID challenge problems and comprehensively quantify their robustness in terms of changes of outfit, scale, and background location. Our quantitative analysis on the realistic, unique aspects of MEVID shows that there are significant remaining challenges in video person ReID and indicates important directions for future research.

Dan Kondratyuk, Liangzhe Yuan, Yandong Li et al.

We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional neural networks (CNNs) are accurate at video recognition but require large computation and memory budgets and do not support online inference, making them difficult to work on mobile devices. We propose a three-step approach to improve computational efficiency while substantially reducing the peak memory usage of 3D CNNs. First, we design a video network search space and employ neural architecture search to generate efficient and diverse 3D CNN architectures. Second, we introduce the Stream Buffer technique that decouples memory from video clip duration, allowing 3D CNNs to embed arbitrary-length streaming video sequences for both training and inference with a small constant memory footprint. Third, we propose a simple ensembling technique to improve accuracy further without sacrificing efficiency. These three progressive techniques allow MoViNets to achieve state-of-the-art accuracy and efficiency on the Kinetics, Moments in Time, and Charades video action recognition datasets. For instance, MoViNet-A5-Stream achieves the same accuracy as X3D-XL on Kinetics 600 while requiring 80% fewer FLOPs and 65% less memory. Code will be made available at https://github.com/tensorflow/models/tree/master/official/vision.

Samuel Li, Pujith Kachana, Prajwal Chidananda et al.

Estimating agent pose and 3D scene structure from multi-camera rigs is a central task in embodied AI applications such as autonomous driving. Recent learned approaches such as DUSt3R have shown impressive performance in multiview settings. However, these models treat images as unstructured collections, limiting effectiveness in scenarios where frames are captured from synchronized rigs with known or inferable structure. To this end, we introduce Rig3R, a generalization of prior multiview reconstruction models that incorporates rig structure when available, and learns to infer it when not. Rig3R conditions on optional rig metadata including camera ID, time, and rig poses to develop a rig-aware latent space that remains robust to missing information. It jointly predicts pointmaps and two types of raymaps: a pose raymap relative to a global frame, and a rig raymap relative to a rig-centric frame consistent across time. Rig raymaps allow the model to infer rig structure directly from input images when metadata is missing. Rig3R achieves state-of-the-art performance in 3D reconstruction, camera pose estimation, and rig discovery, outperforming both traditional and learned methods by 17-45% mAA across diverse real-world rig datasets, all in a single forward pass without post-processing or iterative refinement.

Rui Qian, Yeqing Li, Liangzhe Yuan et al.

This work presents a self-supervised learning framework named TeG to explore Temporal Granularity in learning video representations. In TeG, we sample a long clip from a video and a short clip that lies inside the long clip. We then extract their dense temporal embeddings. The training objective consists of two parts: a fine-grained temporal learning objective to maximize the similarity between corresponding temporal embeddings in the short clip and the long clip, and a persistent temporal learning objective to pull together global embeddings of the two clips. Our study reveals the impact of temporal granularity with three major findings. 1) Different video tasks may require features of different temporal granularities. 2) Intriguingly, some tasks that are widely considered to require temporal awareness can actually be well addressed by temporally persistent features. 3) The flexibility of TeG gives rise to state-of-the-art results on 8 video benchmarks, outperforming supervised pre-training in most cases.

Dan Kondratyuk, Mingxing Tan, Matthew Brown et al.

Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e.g., with different initializations) and aggregating their predictions. This approach is commonly reserved for the largest models, as it is commonly held that increasing the model size provides a more substantial reduction in error than ensembling smaller models. However, we show results from experiments on CIFAR-10 and ImageNet that ensembles can outperform single models with both higher accuracy and requiring fewer total FLOPs to compute, even when those individual models' weights and hyperparameters are highly optimized. Furthermore, this gap in improvement widens as models become large. This presents an interesting observation that output diversity in ensembling can often be more efficient than training larger models, especially when the models approach the size of what their dataset can foster. Instead of using the common practice of tuning a single large model, one can use ensembles as a more flexible trade-off between a model's inference speed and accuracy. This also potentially eases hardware design, e.g., an easier way to parallelize the model across multiple workers for real-time or distributed inference.

Muhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang et al.

Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We analyze this mismatch from a domain adaptation point of view. First of all, we connect existing class-balanced methods for long-tailed classification to target shift, a well-studied scenario in domain adaptation. The connection reveals that these methods implicitly assume that the training data and test data share the same class-conditioned distribution, which does not hold in general and especially for the tail classes. While a head class could contain abundant and diverse training examples that well represent the expected data at inference time, the tail classes are often short of representative training data. To this end, we propose to augment the classic class-balanced learning by explicitly estimating the differences between the class-conditioned distributions with a meta-learning approach. We validate our approach with six benchmark datasets and three loss functions.

Tzu-Ming Harry Hsu, Hang Qi, Matthew Brown

Federated Learning enables visual models to be trained on-device, bringing advantages for user privacy (data need never leave the device), but challenges in terms of data diversity and quality. Whilst typical models in the datacenter are trained using data that are independent and identically distributed (IID), data at source are typically far from IID. Furthermore, differing quantities of data are typically available at each device (imbalance). In this work, we characterize the effect these real-world data distributions have on distributed learning, using as a benchmark the standard Federated Averaging (FedAvg) algorithm. To do so, we introduce two new large-scale datasets for species and landmark classification, with realistic per-user data splits that simulate real-world edge learning scenarios. We also develop two new algorithms (FedVC, FedIR) that intelligently resample and reweight over the client pool, bringing large improvements in accuracy and stability in training. The datasets are made available online.

Tzu-Ming Harry Hsu, Hang Qi, Matthew Brown

Federated Learning enables visual models to be trained in a privacy-preserving way using real-world data from mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly. In this work, we look at the effect such non-identical data distributions has on visual classification via Federated Learning. We propose a way to synthesize datasets with a continuous range of identicalness and provide performance measures for the Federated Averaging algorithm. We show that performance degrades as distributions differ more, and propose a mitigation strategy via server momentum. Experiments on CIFAR-10 demonstrate improved classification performance over a range of non-identicalness, with classification accuracy improved from 30.1% to 76.9% in the most skewed settings.

Mehdi S. M. Sajjadi, Raviteja Vemulapalli, Matthew Brown

Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current state-of-the-art methods process a batch of LR frames to generate a single high-resolution (HR) frame and run this scheme in a sliding window fashion over the entire video, effectively treating the problem as a large number of separate multi-frame super-resolution tasks. This approach has two main weaknesses: 1) Each input frame is processed and warped multiple times, increasing the computational cost, and 2) each output frame is estimated independently conditioned on the input frames, limiting the system's ability to produce temporally consistent results. In this work, we propose an end-to-end trainable frame-recurrent video super-resolution framework that uses the previously inferred HR estimate to super-resolve the subsequent frame. This naturally encourages temporally consistent results and reduces the computational cost by warping only one image in each step. Furthermore, due to its recurrent nature, the proposed method has the ability to assimilate a large number of previous frames without increased computational demands. Extensive evaluations and comparisons with previous methods validate the strengths of our approach and demonstrate that the proposed framework is able to significantly outperform the current state of the art.

Hang Qi, Matthew Brown, David G. Lowe

Human vision is able to immediately recognize novel visual categories after seeing just one or a few training examples. We describe how to add a similar capability to ConvNet classifiers by directly setting the final layer weights from novel training examples during low-shot learning. We call this process weight imprinting as it directly sets weights for a new category based on an appropriately scaled copy of the embedding layer activations for that training example. The imprinting process provides a valuable complement to training with stochastic gradient descent, as it provides immediate good classification performance and an initialization for any further fine-tuning in the future. We show how this imprinting process is related to proxy-based embeddings. However, it differs in that only a single imprinted weight vector is learned for each novel category, rather than relying on a nearest-neighbor distance to training instances as typically used with embedding methods. Our experiments show that using averaging of imprinted weights provides better generalization than using nearest-neighbor instance embeddings.

Yani Ioannou, Duncan Robertson, Darko Zikic et al.

This paper investigates the connections between two state of the art classifiers: decision forests (DFs, including decision jungles) and convolutional neural networks (CNNs). Decision forests are computationally efficient thanks to their conditional computation property (computation is confined to only a small region of the tree, the nodes along a single branch). CNNs achieve state of the art accuracy, thanks to their representation learning capabilities. We present a systematic analysis of how to fuse conditional computation with representation learning and achieve a continuum of hybrid models with different ratios of accuracy vs. efficiency. We call this new family of hybrid models conditional networks. Conditional networks can be thought of as: i) decision trees augmented with data transformation operators, or ii) CNNs, with block-diagonal sparse weight matrices, and explicit data routing functions. Experimental validation is performed on the common task of image classification on both the CIFAR and Imagenet datasets. Compared to state of the art CNNs, our hybrid models yield the same accuracy with a fraction of the compute cost and much smaller number of parameters.