incerto.sp.SelfAdaptiveTraining

class incerto.sp.SelfAdaptiveTraining(backbone, num_classes, alpha_start=0.0, alpha_end=0.9, warmup_epochs=5)

Bases: BaseSelectivePredictor

Self-Adaptive Training for better calibration and selective prediction.

Trains with adaptive soft labels that blend ground truth and model predictions:

y_adaptive = (1 - alpha) * y_hard + alpha * softmax(logits)

This improves calibration naturally during training, making the model better at knowing when to reject/abstain on uncertain samples.

Reference:

Huang et al., “Self-Adaptive Training: beyond Empirical Risk Minimization” NeurIPS 2020.

Parameters:

• backbone (Module)

• num_classes (int)

• alpha_start (float)

• alpha_end (float)

• warmup_epochs (int)

__init__(backbone, num_classes, alpha_start=0.0, alpha_end=0.9, warmup_epochs=5)

Parameters:

• backbone (Module) – The base model to train

• num_classes (int) – Number of classes

• alpha_start (float) – Initial alpha value (0 = pure hard labels)

• alpha_end (float) – Final alpha value (higher = more self-supervision)

• warmup_epochs (int) – Number of epochs before starting SAT

Methods

__init__(backbone, num_classes[, ...])
add_module(name, module)	Add a child module to the current module.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
confidence_from_logits(logits)	Extract confidence scores from logits.
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(x, *[, return_confidence])	Forward pass with optional confidence scores.
get_alpha(epoch, total_epochs)	Compute current alpha value based on training progress.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
modules()	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
reject(confidence, threshold)	Determine which samples should be rejected based on confidence.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
sat_loss(logits, targets, alpha)	Compute Self-Adaptive Training loss.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module[, strict])	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

Attributes

T_destination
call_super_init
dump_patches
training

__init__(backbone, num_classes, alpha_start=0.0, alpha_end=0.9, warmup_epochs=5)

Parameters:

• backbone (Module) – The base model to train

• num_classes (int) – Number of classes

• alpha_start (float) – Initial alpha value (0 = pure hard labels)

• alpha_end (float) – Final alpha value (higher = more self-supervision)

• warmup_epochs (int) – Number of epochs before starting SAT

get_alpha(epoch, total_epochs)

Compute current alpha value based on training progress.

Parameters:

• epoch (int) – Current epoch number

• total_epochs (int) – Total number of training epochs

Return type:

float

Returns:

Alpha value for blending hard and soft labels

sat_loss(logits, targets, alpha)

Compute Self-Adaptive Training loss.

Parameters:

• logits (Tensor) – Model predictions (batch_size, num_classes)

• targets (Tensor) – Ground truth labels (batch_size,)

• alpha (float) – Mixing coefficient for soft labels

Return type:

Tensor

Returns:

SAT loss value