AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning

Multi-task learning is an open and challenging problem in computer vision. The typical way of conducting multi-task learning with deep neural networks is either through handcrafting schemes that share all initial layers and branch out at an adhoc point or through using separate task-specific networks with an additional feature sharing/fusion mechanism. Unlike existing methods, we propose an adaptive sharing approach, called AdaShare, that decides what to share across which tasks for achieving the best recognition accuracy, while taking resource efficiency into account. Specifically, our main idea is to learn the sharing pattern through a task-specific policy that selectively chooses which layers to execute for a given task in the multi-task network. We efficiently optimize the task-specific policy jointly with the network weights using standard back-propagation. Experiments on three challenging and diverse benchmark datasets with a variable number of tasks well demonstrate the efficacy of our approach over state-of-the-art methods.

Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets

Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. In particular, skin cancer classification models have achieved performance higher than trained expert dermatologists. However, no attempt has been made to evaluate the consistency in performance of machine learning models across populations with varying skin tones. In this paper, we present an approach to estimate skin tone in benchmark skin disease datasets, and investigate whether model performance is dependent on this measure. Specifically, we use individual typology angle (ITA) to approximate skin tone in dermatology datasets. We look at the distribution of ITA values to better understand skin color representation in two benchmark datasets: 1) the ISIC 2018 Challenge dataset, a collection of dermoscopic images of skin lesions for the detection of skin cancer, and 2) the SD-198 dataset, a collection of clinical images capturing a wide variety of skin diseases. To estimate ITA, we first develop segmentation models to isolate non-diseased areas of skin. We find that the majority of the data in the the two datasets have ITA values between 34.5{\deg} and 48{\deg}, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets. We also find no measurable correlation between performance of machine learning model and ITA values, though more comprehensive data is needed for further validation.

Consistent Cross-view Matching for Unsupervised Person Re-identification

Most existing unsupervised person re-identificationmethods focus on learning an identity discriminative feature em-bedding for efficiently representing images of different persons.However, higher-order relationships across the entire cameranetwork are often ignored leading to contradictory outputs whenthe results of different camera pairs are combined. In this paper,we address this problem by proposing a consistent cross-viewmatching framework for unsupervised person re-identificationby exploiting more reliable positive image pairs in a cameranetwork. Specifically, we first construct a bipartite graph foreach pair of cameras, in which each node denotes a person, andthen graph matching is used to obtain optimal global matchesacross camera pairs. Thereafter, loop consistent and transitiveinference consistent constraints are introduced into the cross-view matches, which consider similarity relationshipsacross theentire camera networkto increase confidence in the matched/non-matched pairs. We then train distance metric models for eachcamera pair using the reliably matched image pairs. Finally,we embed the cross-view matching method into an iterativeupdating framework that iterates between the consistent cross-view matching and the cross-view distance metric learning. Wedemonstrate the superiority of the proposed method over thestate-of-the-art unsupervised person re-identification methodson three benchmark datasets such as Market1501, MARS andDukeMTMC-VideoReID datasets

Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval

Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across modalities, most of these methods are plagued by the issue of training with small-scale datasets covering a limited number of images with ground-truth sentences. Moreover, it is extremely expensive to create a larger dataset by annotating millions of images with sentences and may lead to a biased model. Inspired by the recent success of webly supervised learning in deep neural networks, we capitalize on readily-available web images with noisy annotations to learn robust image-text joint representation. Specifically, our main idea is to leverage web images and corresponding tags, along with fully annotated datasets, in training for learning the visual-semantic joint embedding. We propose a two-stage approach for the task that can augment a typical supervised pair-wise ranking loss based formulation with weakly-annotated web images to learn a more robust visual-semantic embedding. Experiments on two standard benchmark datasets demonstrate that our method achieves a significant performance gain in image-text retrieval compared to state-of-the-art approaches.

Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias

While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts. Our analysis identifies an important but long overlooked issue of existing visual emotion benchmarks in the form of dataset biases. We design a series of tests to show and measure how such dataset biases obstruct learning a generalizable emotion recognition model. Based on our analysis, we propose a webly supervised approach by leveraging a large quantity of stock image data. Our approach uses a simple yet effective curriculum guided training strategy for learning discriminative emotion features. We discover that the models learned using our large scale stock image dataset exhibit significantly better generalization ability than the existing datasets without the manual collection of even a single label. Moreover, visual representation learned using our approach holds a lot of promise across a variety of tasks on different image and video datasets.

FFNet: Video Fast-Forwarding via Reinforcement Learning

For many applications with limited computation, communication, storage and energy resources, there is an imperative need of computer vision methods that could select an informative subset of the input video for efficient processing at or near real time. In the literature, there are two relevant groups of approaches: generating a trailer for a video or fast-forwarding while watching/processing the video. The first group is supported by video summarization techniques, which require processing of the entire video to select an important subset for showing to users. In the second group, current fast-forwarding methods depend on either manual control or automatic adaptation of playback speed, which often do not present an accurate representation and may still require processing of every frame. In this paper, we introduce FastForwardNet (FFNet), a reinforcement learning agent that gets inspiration from video summarization and does fast-forwarding differently. It is an online framework that automatically fast-forwards a video and presents a representative subset of frames to users on the fly. It does not require processing the entire video, but just the portion that is selected by the fast-forward agent, which makes the process very computationally efficient. The online nature of our proposed method also enables the users to begin fast-forwarding at any point of the video. Experiments on two real-world datasets demonstrate that our method can provide better representation of the input video with much less processing requirement.

Diversity-aware Multi-Video Summarization

Most video summarization approaches have focused on extracting a summary from a single video; we propose an unsupervised framework for summarizing a collection of videos. We observe that each video in the collection may contain some information that other videos do not have, and thus exploring the underlying complementarity could be beneficial in creating a diverse informative summary. We develop a novel diversity-aware sparse optimization method for multi-video summarization by exploring the complementarity within the videos. Our approach extracts a multi-video summary which is both interesting and representative in describing the whole video collection. To efficiently solve our optimization problem, we develop an alternating minimization algorithm that minimizes the overall objective function with respect to one video at a time while fixing the other videos. Moreover, we introduce a new benchmark dataset, Tour20, that contains 140 videos with multiple human created summaries, which were acquired in a controlled experiment. Finally, by extensive experiments on the new Tour20 dataset and several other multi-view datasets, we show that the proposed approach clearly outperforms the state-of-the-art methods on the two problems-topic-oriented video summarization and multi-view video summarization in a camera network.

Multi-View Surveillance Video Summarization via Joint Embedding and Sparse Optimization

Most traditional video summarization methods are designed to generate effective summaries for single-view videos, and thus they cannot fully exploit the complicated intra and inter-view correlations in summarizing multi-view videos in a camera network. In this paper, with the aim of summarizing multi-view videos, we introduce a novel unsupervised framework via joint embedding and sparse representative selection. The objective function is two-fold. The first is to capture the multi-view correlations via an embedding, which helps in extracting a diverse set of representatives. The second is to use a `2;1- norm to model the sparsity while selecting representative shots for the summary. We propose to jointly optimize both of the objectives, such that embedding can not only characterize the correlations, but also indicate the requirements of sparse representative selection. We present an efficient alternating algorithm based on half-quadratic minimization to solve the proposed non-smooth and non-convex objective with convergence analysis. A key advantage of the proposed approach with respect to the state-of-the-art is that it can summarize multi-view videos without assuming any prior correspondences/alignment between them, e.g., uncalibrated camera networks. Rigorous experiments on several multi-view datasets demonstrate that our approach clearly outperforms the state-of-the-art methods.

Collaborative Summarization of Topic-Related Videos

Large collections of videos are grouped into clusters by a topic keyword, such as Eiffel Tower or Surfing, with many important visual concepts repeating across them. Such a topically close set of videos have mutual influence on each other, which could be used to summarize one of them by exploiting information from others in the set. We build on this intuition to develop a novel approach to extract a summary that simultaneously captures both important particularities arising in the given video, as well as, generalities identified from the set of videos. The topic-related videos provide visual context to identify the important parts of the video being summarized. We achieve this by developing a collaborative sparse optimization method which can be efficiently solved by a half-quadratic minimization algorithm. Our work builds upon the idea of collaborative techniques from information retrieval and natural language processing, which typically use the attributes of other similar objects to predict the attribute of a given object. Experiments on two challenging and diverse datasets well demonstrate the efficacy of our approach over state-of-the-art methods.

Unsupervised Adaptive Re-identification in Open World Dynamic Camera Networks

Person re-identification is an open and challenging problem in computer vision. Existing approaches have concentrated on either designing the best feature representation or learning optimal matching metrics in a static setting where the number of cameras are fixed in a network. Most approaches have neglected the dynamic and open world nature of the re-identification problem, where a new camera may be temporarily inserted into an existing system to get additional information. To address such a novel and very practical problem, we propose an unsupervised adaptation scheme for re-identification models in a dynamic camera network. First, we formulate a domain perceptive re-identification method based on geodesic flow kernel that can effectively find the best source camera (already installed) to adapt with a newly introduced target camera, without requiring a very expensive training phase. Second, we introduce a transitive inference algorithm for re-identification that can exploit the information from best source camera to improve the accuracy across other camera pairs in a network of multiple cameras. Extensive experiments on four benchmark datasets demonstrate that the proposed approach significantly outperforms the state-of-the-art unsupervised learning based alternatives whilst being extremely efficient to compute.