Ross B. Girshick

Object Detection with Discriminatively Trained Part-Based Models

We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL data sets. Our system relies on new methods for discriminative training with partially labeled data. We combine a margin-sensitive approach for data-mining hard negative examples with a formalism we call latent SVM. A latent SVM is a reformulation of MI--SVM in terms of latent variables. A latent SVM is semiconvex, and the training problem becomes convex once latent information is specified for the positive examples. This leads to an iterative training algorithm that alternates between fixing latent values for positive examples and optimizing the latent SVM objective function.

Caffe: Convolutional Architecture for Fast Feature Embedding

Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Caffe fits industry and internet-scale media needs by CUDA GPU computation, processing over 40 million images a day on a single K40 or Titan GPU (approx 2 ms per image). By separating model representation from actual implementation, Caffe allows experimentation and seamless switching among platforms for ease of development and deployment from prototyping machines to cloud environments. Caffe is maintained and developed by the Berkeley Vision and Learning Center (BVLC) with the help of an active community of contributors on GitHub. It powers ongoing research projects, large-scale industrial applications, and startup prototypes in vision, speech, and multimedia.

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

Fast R-CNN

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9x faster than R-CNN, is 213x faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3x faster, tests 10x faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https://github.com/rbgirshick/fast-rcnn.

You Only Look Once: Unified, Real-Time Object Detection

We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

Learning Rich Features from RGB-D Images for Object Detection and Segmentation

In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features. We propose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for each pixel in addition to the horizontal disparity. We demonstrate that this geocentric embedding works better than using raw depth images for learning feature representations with convolutional neural networks. Our final object detection system achieves an average precision of 37.3%, which is a 56% relative improvement over existing methods. We then focus on the task of instance segmentation where we label pixels belonging to object instances found by our detector. For this task, we propose a decision forest approach that classifies pixels in the detection window as foreground or background using a family of unary and binary tests that query shape and geocentric pose features. Finally, we use the output from our object detectors in an existing superpixel classification framework for semantic scene segmentation and achieve a 24% relative improvement over current state-of-the-art for the object categories that we study. We believe advances such as those represented in this paper will facilitate the use of perception in fields like robotics.

Cascade object detection with deformable part models

We describe a general method for building cascade classifiers from part-based deformable models such as pictorial structures. We focus primarily on the case of star-structured models and show how a simple algorithm based on partial hypothesis pruning can speed up object detection by more than one order of magnitude without sacrificing detection accuracy. In our algorithm, partial hypotheses are pruned with a sequence of thresholds. In analogy to probably approximately correct (PAC) learning, we introduce the notion of probably approximately admissible (PAA) thresholds. Such thresholds provide theoretical guarantees on the performance of the cascade method and can be computed from a small sample of positive examples. Finally, we outline a cascade detection algorithm for a general class of models defined by a grammar formalism. This class includes not only tree-structured pictorial structures but also richer models that can represent each part recursively as a mixture of other parts.

Hypercolumns for object segmentation and fine-grained localization

Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a feature representation. However, the information in this layer may be too coarse spatially to allow precise localization. On the contrary, earlier layers may be precise in localization but will not capture semantics. To get the best of both worlds, we define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel. Using hypercolumns as pixel descriptors, we show results on three fine-grained localization tasks: simultaneous detection and segmentation [22], where we improve state-of-the-art from 49.7 mean APr [22] to 60.0, keypoint localization, where we get a 3.3 point boost over [20], and part labeling, where we show a 6.6 point gain over a strong baseline.

Simultaneous Detection and Segmentation

We aim to detect all instances of a category in an image and, for each instance, mark the pixels that belong to it. We call this task Simultaneous Detection and Segmentation (SDS). Unlike classical bounding box detection, SDS requires a segmentation and not just a box. Unlike classical semantic segmentation, we require individual object instances. We build on recent work that uses convolutional neural networks to classify category-independent region proposals (R-CNN [16]), introducing a novel architecture tailored for SDS. We then use category-specific, top-down figure-ground predictions to refine our bottom-up proposals. We show a 7 point boost (16% relative) over our baselines on SDS, a 5 point boost (10% relative) over state-of-the-art on semantic segmentation, and state-of-the-art performance in object detection. Finally, we provide diagnostic tools that unpack performance and provide directions for future work.

Visual object detection with deformable part models

We describe a state-of-the-art system for finding objects in cluttered images. Our system is based on deformable models that represent objects using local part templates and geometric constraints on the locations of parts. We reduce object detection to classification with latent variables. The latent variables introduce invariances that make it possible to detect objects with highly variable appearance. We use a generalization of support vector machines to incorporate latent information during training. This has led to a general framework for discriminative training of classifiers with latent variables. Discriminative training benefits from large training datasets. In practice we use an iterative algorithm that alternates between estimating latent values for positive examples and solving a large convex optimization problem. Practical optimization of this large convex problem can be done using active set techniques for adaptive subsampling of the training data.