Self-supervised visual learning from interactions with objects

Self-supervised learning (SSL) has revolutionized visual representation learning, but has not achieved the robustness of human vision. A reason for this could be that SSL does not leverage all the data available to humans during learning. When learning about an object, humans often purposefully turn or move around objects and research suggests that these interactions can substantially enhance their learning. Here we explore whether such object-related actions can boost SSL. For this, we extract the actions performed to change from one ego-centric view of an object to another in four video datasets. We then introduce a new loss function to learn visual and action embeddings by aligning the performed action with the representations of two images extracted from the same clip. This permits the performed actions to structure the latent visual representation. Our experiments show that our method consistently outperforms previous methods on downstream category recognition. In our analysis, we find that the observed improvement is associated with a better viewpoint-wise alignment of different objects from the same category. Overall, our work demonstrates that embodied interactions with objects can improve SSL of object categories.

Self-Supervised Learning of Color Constancy

Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions. While CC and its limitations have been carefully characterized in humans, it is still unclear how the visual system acquires this ability during development. Here, we present a first study showing that CC develops in a neural network trained in a self-supervised manner through an invariance learning objective. During learning, objects are presented under changing illuminations, while the network aims to map subsequent views of the same object onto close-by latent representations. This gives rise to representations that are largely invariant to the illumination conditions, offering a plausible example of how CC could emerge during human cognitive development via a form of self-supervised learning.

MIMo: A Multi-Modal Infant Model for Studying Cognitive Development

Human intelligence and human consciousness emerge gradually during the process of cognitive development. Understanding this development is an essential aspect of understanding the human mind and may facilitate the construction of artificial minds with similar properties. Importantly, human cognitive development relies on embodied interactions with the physical and social environment, which is perceived via complementary sensory modalities. These interactions allow the developing mind to probe the causal structure of the world. This is in stark contrast to common machine learning approaches, e.g., for large language models, which are merely passively ``digesting'' large amounts of training data, but are not in control of their sensory inputs. However, computational modeling of the kind of self-determined embodied interactions that lead to human intelligence and consciousness is a formidable challenge. Here we present MIMo, an open-source multi-modal infant model for studying early cognitive development through computer simulations. MIMo's body is modeled after an 18-month-old child with detailed five-fingered hands. MIMo perceives its surroundings via binocular vision, a vestibular system, proprioception, and touch perception through a full-body virtual skin, while two different actuation models allow control of his body. We describe the design and interfaces of MIMo and provide examples illustrating its use. All code is available at https://github.com/trieschlab/MIMo .

Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Play

Infants' ability to recognize and categorize objects develops gradually. The second year of life is marked by both the emergence of more semantic visual representations and a better understanding of word meaning. This suggests that language input may play an important role in shaping visual representations. However, even in suitable contexts for word learning like dyadic play sessions, caregivers utterances are sparse and ambiguous, often referring to objects that are different from the one to which the child attends. Here, we systematically investigate to what extent caregivers' utterances can nevertheless enhance visual representations. For this we propose a computational model of visual representation learning during dyadic play. We introduce a synthetic dataset of ego-centric images perceived by a toddler-agent that moves and rotates toy objects in different parts of its home environment while hearing caregivers' utterances, modeled as captions. We propose to model toddlers' learning as simultaneously aligning representations for 1) close-in-time images and 2) co-occurring images and utterances. We show that utterances with statistics matching those of real caregivers give rise to representations supporting improved category recognition. Our analysis reveals that a small decrease/increase in object-relevant naming frequencies can drastically impact the learned representations. This affects the attention on object names within an utterance, which is required for efficient visuo-linguistic alignment. Overall, our results support the hypothesis that caregivers' naming utterances can improve toddlers' visual representations.

CIPER: Combining Invariant and Equivariant Representations Using Contrastive and Predictive Learning

Self-supervised representation learning (SSRL) methods have shown great success in computer vision. In recent studies, augmentation-based contrastive learning methods have been proposed for learning representations that are invariant or equivariant to pre-defined data augmentation operations. However, invariant or equivariant features favor only specific downstream tasks depending on the augmentations chosen. They may result in poor performance when a downstream task requires the counterpart of those features (e.g., when the task is to recognize hand-written digits while the model learns to be invariant to in-plane image rotations rendering it incapable of distinguishing "9" from "6"). This work introduces Contrastive Invariant and Predictive Equivariant Representation learning (CIPER). CIPER comprises both invariant and equivariant learning objectives using one shared encoder and two different output heads on top of the encoder. One output head is a projection head with a state-of-the-art contrastive objective to encourage invariance to augmentations. The other is a prediction head estimating the augmentation parameters, capturing equivariant features. Both heads are discarded after training and only the encoder is used for downstream tasks. We evaluate our method on static image tasks and time-augmented image datasets. Our results show that CIPER outperforms a baseline contrastive method on various tasks, especially when the downstream task requires the encoding of augmentation-related information.

Sequence and Circle: Exploring the Relationship Between Patches

The vision transformer (ViT) has achieved state-of-the-art results in various vision tasks. It utilizes a learnable position embedding (PE) mechanism to encode the location of each image patch. However, it is presently unclear if this learnable PE is really necessary and what its benefits are. This paper explores two alternative ways of encoding the location of individual patches that exploit prior knowledge about their spatial arrangement. One is called the sequence relationship embedding (SRE), and the other is called the circle relationship embedding (CRE). Among them, the SRE considers all patches to be in order, and adjacent patches have the same interval distance. The CRE considers the central patch as the center of the circle and measures the distance of the remaining patches from the center based on the four neighborhoods principle. Multiple concentric circles with different radii combine different patches. Finally, we implemented these two relations on three classic ViTs and tested them on four popular datasets. Experiments show that SRE and CRE can replace PE to reduce the random learnable parameters while achieving the same performance. Combining SRE or CRE with PE gets better performance than only using PE.

Time to augment contrastive learning

Biological vision systems are unparalleled in their ability to learn visual representations without supervision. In machine learning, contrastive learning (CL) has led to major advances in forming object representations in an unsupervised fashion. These systems learn representations invariant to augmentation operations over images, like cropping or flipping. In contrast, biological vision systems exploit the temporal structure of the visual experience. This gives access to augmentations not commonly used in CL, like watching the same object from multiple viewpoints or against different backgrounds. Here, we systematically investigate and compare the potential benefits of such time-based augmentations for learning object categories. Our results show that time-based augmentations achieve large performance gains over state-of-the-art image augmentations. Specifically, our analyses reveal that: 1) 3-D object rotations drastically improve the learning of object categories; 2) viewing objects against changing backgrounds is vital for learning to discard background-related information. Overall, we conclude that time-based augmentations can greatly improve contrastive learning, narrowing the gap between artificial and biological vision systems.

Embodied vision for learning object representations

Recent time-contrastive learning approaches manage to learn invariant object representations without supervision. This is achieved by mapping successive views of an object onto close-by internal representations. When considering this learning approach as a model of the development of human object recognition, it is important to consider what visual input a toddler would typically observe while interacting with objects. First, human vision is highly foveated, with high resolution only available in the central region of the field of view. Second, objects may be seen against a blurry background due to infants' limited depth of field. Third, during object manipulation a toddler mostly observes close objects filling a large part of the field of view due to their rather short arms. Here, we study how these effects impact the quality of visual representations learnt through time-contrastive learning. To this end, we let a visually embodied agent "play" with objects in different locations of a near photo-realistic flat. During each play session the agent views an object in multiple orientations before turning its body to view another object. The resulting sequence of views feeds a time-contrastive learning algorithm. Our results show that visual statistics mimicking those of a toddler improve object recognition accuracy in both familiar and novel environments. We argue that this effect is caused by the reduction of features extracted in the background, a neural network bias for large features in the image and a greater similarity between novel and familiar background regions. We conclude that the embodied nature of visual learning may be crucial for understanding the development of human object perception.

Multiple Instance Learning for Brain Tumor Detection from Magnetic Resonance Spectroscopy Data

We apply deep learning (DL) on Magnetic resonance spectroscopy (MRS) data for the task of brain tumor detection. Medical applications often suffer from data scarcity and corruption by noise. Both of these problems are prominent in our data set. Furthermore, a varying number of spectra are available for the different patients. We address these issues by considering the task as a multiple instance learning (MIL) problem. Specifically, we aggregate multiple spectra from the same patient into a "bag" for classification and apply data augmentation techniques. To achieve the permutation invariance during the process of bagging, we proposed two approaches: (1) to apply min-, max-, and average-pooling on the features of all samples in one bag and (2) to apply an attention mechanism. We tested these two approaches on multiple neural network architectures. We demonstrate that classification performance is significantly improved when training on multiple instances rather than single spectra. We propose a simple oversampling data augmentation method and show that it could further improve the performance. Finally, we demonstrate that our proposed model outperforms manual classification by neuroradiologists according to most performance metrics.

Recurrent Feedback Improves Recognition of Partially Occluded Objects

Recurrent connectivity in the visual cortex is believed to aid object recognition for challenging conditions such as occlusion. Here we investigate if and how artificial neural networks also benefit from recurrence. We compare architectures composed of bottom-up, lateral and top-down connections and evaluate their performance using two novel stereoscopic occluded object datasets. We find that classification accuracy is significantly higher for recurrent models when compared to feedforward models of matched parametric complexity. Additionally we show that for challenging stimuli, the recurrent feedback is able to correctly revise the initial feedforward guess.