Abstract: Human detection is fundamental in many machine vision applications, like video surveillance, driving assistance, action recognition and scene understanding. However in most of these applications real-time performance is necessary and this is not achieved yet by current detection methods.
This paper presents a new method for human detection based on a multiresolution cascade of Histograms of Oriented Gradients (HOG) that can highly reduce the computational cost of detection search without affecting accuracy. The method consists of a cascade of sliding window detectors. Each detector is a linear Support Vector Machine (SVM) composed of HOG features at different resolutions, from coarse at the first level to fine at the last one.
In contrast to previous methods, our approach uses a non-uniform stride of the sliding window that is defined by the feature resolution and allows the detection to be incrementally refined as going from coarse-to-fine resolution. In this way, the speed-up of the cascade is not only due to the fewer number of features computed at the first levels of the cascade, but also to the reduced number of windows that need to be evaluated at the coarse resolution. Experimental results show that our method reaches a detection rate comparable with the state-of-the-art of detectors based on HOG features, while at the same time the detection search is up to 23 times faster.

Abstract: We present a method that can dramatically accelerate object detection with part based models. The method is based on the observation that the cost of detection is likely to be dominated by the cost of matching each part to the image, and not by the cost of computing the optimal configuration of the parts as commonly assumed. Therefore accelerating detection requires minimizing the number of
part-to-image comparisons. To this end we propose a multiple-resolutions hierarchical part based model and a corresponding coarse-to-fine inference procedure that recursively eliminates from the search space unpromising part
placements. The method yields a ten-fold speedup over the standard dynamic programming approach and is complementary to the cascade-of-parts approach of [9]. Compared to the latter, our method does not have parameters to be determined empirically, which simplifies its use during the training of the model. Most importantly, the two techniques can be combined to obtain a very significant speedup, of two orders of magnitude in some cases. We evaluate our method extensively on the PASCAL VOC and INRIA datasets, demonstrating a very high increase in the detection speed with little degradation of the accuracy.

Abstract: We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of previously learned tasks. This is often achieved via exemplar replay which can help recalibrate previous task classifiers to the feature drift which occurs when learning new tasks. Exemplar replay, however, comes at the cost of retaining samples from previous tasks which for many applications may not be possible. To address the problem of continual ViT training, we first propose gated class-attention to minimize the drift in the final ViT transformer block. This mask-based gating is applied to class-attention mechanism of the last transformer block and strongly regulates the weights crucial for previous tasks. Importantly, gated class-attention does not require the task-ID during inference, which distinguishes it from other parameter isolation methods. Secondly, we propose a new method of feature drift compensation that accommodates feature drift in the backbone when learning new tasks. The combination of gated class-attention and cascaded feature drift compensation allows for plasticity towards new tasks while limiting forgetting of previous ones. Extensive experiments performed on CIFAR-100, Tiny-ImageNet and ImageNet100 demonstrate that our exemplar-free method obtains competitive results when compared to rehearsal based ViT methods.

Abstract: In this paper we present a deep learning method to estimate the illuminant of an image. Our model is not trained with illuminant annotations, but with the objective of improving performance on an auxiliary task such as object recognition. To the best of our knowledge, this is the first example of a deep
learning architecture for illuminant estimation that is trained without ground truth illuminants. We evaluate our solution on standard datasets for color constancy, and compare it with state of the art methods. Our proposal is shown to outperform most deep learning methods in a cross-dataset evaluation
setup, and to present competitive results in a comparison with parametric solutions.

Abstract: Self-supervised learning (SSL) is a powerful technique for learning robust representations from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo are able to reach quality on par with supervised approaches. However, this invariance may be harmful to solving some downstream tasks which depend on traits affected by augmentations used during pretraining, such as color. In this paper, we propose to foster sensitivity to such characteristics in the representation space by modifying the projector network, a common component of self-supervised architectures. Specifically, we supplement the projector with information about augmentations applied to images. In order for the projector to take advantage of this auxiliary conditioning when solving the SSL task, the feature extractor learns to preserve the augmentation information in its representations. Our approach, coined Conditional Augmentation-aware Self-supervised Learning (CASSLE), is directly applicable to typical joint-embedding SSL methods regardless of their objective functions. Moreover, it does not require major changes in the network architecture or prior knowledge of downstream tasks. In addition to an analysis of sensitivity towards different data augmentations, we conduct a series of experiments, which show that CASSLE improves over various SSL methods, reaching state-of-the-art performance in multiple downstream tasks.

Abstract: Several studies have recorded color emotions in subjects viewing uniform color (UC) samples. We conduct an experiment to measure and model how these color emotions change when texture is added to the color samples. Using a computer monitor, our subjects arrange samples along four scales: warm–cool, masculine–feminine, hard–soft, and heavy–light. Three sample types of increasing visual complexity are used: UC, grayscale textures, and color textures (CTs). To assess the intraobserver variability, the experiment is repeated after 1 week. Our results show that texture fully determines the responses on the Hard-Soft scale, and plays a role of decreasing weight for the masculine–feminine, heavy–light, and warm–cool scales. Using some 25,000 observer responses, we derive color emotion functions that predict the group-averaged scale responses from the samples' color and texture parameters. For UC samples, the accuracy of our functions is significantly higher (average R2 = 0.88) than that of previously reported functions applied to our data. The functions derived for CT samples have an accuracy of R2 = 0.80. We conclude that when textured samples are used in color emotion studies, the psychological responses may be strongly affected by texture. © 2010 Wiley Periodicals, Inc. Col Res Appl, 2010

Abstract: Intrinsic characterization of scenes is often the best way to overcome the illumination variability artifacts that complicate most computer vision problems, from 3D reconstruction to object or material recognition. This paper examines the deficiency of existing intrinsic image models to accurately account for the effects of illuminant color and sensor characteristics in the estimation of intrinsic images and presents a generic framework which incorporates insights from color constancy research to the intrinsic image decomposition problem. The proposed mathematical formulation includes information about the color of the illuminant and the effects of the camera sensors, both of which modify the observed color of the reflectance of the objects in the scene during the acquisition process. By modeling these effects, we get a “truly intrinsic” reflectance image, which we call absolute reflectance, which is invariant to changes of illuminant or camera sensors. This model allows us to represent a wide range of intrinsic image decompositions depending on the specific assumptions on the geometric properties of the scene configuration and the spectral properties of the light source and the acquisition system, thus unifying previous models in a single general framework. We demonstrate that even partial information about sensors improves significantly the estimated reflectance images, thus making our method applicable for a wide range of sensors. We validate our general intrinsic image framework experimentally with both synthetic data and natural images.